upd

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Kaiju-11B-Q4_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,16 @@
 ---
 license: cc-by-4.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
 ---
+
+Just for fun, I tried to create an imatrix model for Kaiju-11B. (https://huggingface.co/Himitsui/Kaiju-11B)
+
+I thought it wouldn’t work, since I only have a laptop with an Nvidia 3060 with 6GB of memory, but strangely enough, I was able to create a couple of models thanks to one script.
+
+Here it is: https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script
+
+According to the recommendations, my laptop was not suitable. I don’t know how it all works, maybe these were just recommendations to make quantization happen quickly. (it took me about an hour and a half to create the imatrix.bat file, but the quantization was fast)
+If anyone is interested, download and see how they work, this was done purely for fun, no more no less.